| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 101, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.999516282291988e-05, | |
| "loss": 0.8295, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.987930439740757e-05, | |
| "loss": 1.3536, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.95201310753273e-05, | |
| "loss": 0.4367, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.8931150161867917e-05, | |
| "loss": 0.3533, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.8126579138282502e-05, | |
| "loss": 0.3654, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.7125839641475074e-05, | |
| "loss": 0.3764, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.595308864276666e-05, | |
| "loss": 0.3401, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.4636635319853274e-05, | |
| "loss": 0.3539, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.3208257698153677e-05, | |
| "loss": 0.3999, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1702435557223988e-05, | |
| "loss": 0.3299, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0155518119203511e-05, | |
| "loss": 0.2854, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 8.604846610560771e-06, | |
| "loss": 0.3799, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.0878528777274814e-06, | |
| "loss": 0.3321, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5.64115581524629e-06, | |
| "loss": 0.369, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.299677417862174e-06, | |
| "loss": 0.3302, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.0957997942825337e-06, | |
| "loss": 0.3035, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.058583491552465e-06, | |
| "loss": 0.3097, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.2130659990073146e-06, | |
| "loss": 0.3248, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.796573653001091e-07, | |
| "loss": 0.2946, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.7364751777736334e-07, | |
| "loss": 0.2796, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.837177080119215e-09, | |
| "loss": 0.3042, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.32460731267929077, | |
| "eval_runtime": 8.9558, | |
| "eval_samples_per_second": 20.099, | |
| "eval_steps_per_second": 0.335, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 101, | |
| "total_flos": 709723422720.0, | |
| "train_loss": 0.38626466322653363, | |
| "train_runtime": 734.6882, | |
| "train_samples_per_second": 2.183, | |
| "train_steps_per_second": 0.137 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 101, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 709723422720.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |